Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3370 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.8281. Min Act: -0.0001

Data Index: 165279 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.6195. Min Act: -0.0001

Data Index: 1257195 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.5326. Min Act: -0.0001

Data Index: 464398 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.5549. Min Act: -0.0001

Data Index: 1195452 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.6116. Min Act: -0.0000

Data Index: 699813 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.5354. Min Act: -0.0001

Data Index: 816251 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.5229. Min Act: -0.0000

Data Index: 131015 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.4737. Min Act: -0.0001

Data Index: 239398 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.5115. Min Act: -0.0001

Data Index: 604000 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.4822. Min Act: -0.0001

Data Index: 828167 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.5015. Min Act: -0.0000

Data Index: 152973 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.4627. Min Act: -0.0000

Data Index: 475977 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.4772. Min Act: -0.0000

Data Index: 674743 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.4720. Min Act: -0.0000

Data Index: 314921 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.4711. Min Act: -0.0000

Data Index: 1253347 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.4861. Min Act: -0.0000

Data Index: 150817 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.4650. Min Act: -0.0000

Data Index: 444347 (C4 (Web Text))

Max Activating Token Index: 622

Text #17

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.4516. Min Act: -0.0000

Data Index: 1250926 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.4580. Min Act: -0.0000

Data Index: 573488 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.4587. Min Act: -0.0001

Data Index: 794360 (C4 (Web Text))

Max Activating Token Index: 1013